ODSL Forum: Identification of b-jets Using Graph Neural Networks with the ATLAS Detector at the LHC: A Use Case for Machine Learning-Based Reconstruction Techniques

by Prof. Francesco Di Bello (University of Genova)

Friday 2 Jun 2023, 15:00 → 16:00 Europe/Berlin

Basement Seminar Room (Origins Building)

Abstract: In recent years, machine learning techniques have demonstrated remarkable success in various scientific domains. In the field of high-energy physics, the use of machine learning algorithms for event reconstruction has gained significant attention. This seminar focuses on one specific application: the identification of b-jets using graph neural networks (GNNs) with the ATLAS detector at the Large Hadron Collider (LHC).
B-jets, which arise from the hadronization of b-quarks, play a crucial role in a wide range of physics analyses, including searches for new particles and precision measurements of Standard Model processes. Accurate identification and efficient reconstruction of b-jets are essential for maximizing the sensitivity and precision of such analyses.
During the seminar, we will delve into the challenges associated with b-jet identification and explore how machine learning-based reconstruction techniques, specifically GNNs, can effectively address these challenges. Furthermore, I will conclude by discussing the challenges of particle reconstruction and, in a broader context, the application of graph neural networks and their potential impact on improving the reconstruction of complex particle collisions.